ggplotly() and plot_ly()plot_geo()We will work with two Starbucks datasets, one on the store locations (global) and one for the nutritional data for their food and drink items. We will do some text analysis of the menu items.
str(sb_locs)
## spc_tbl_ [25,600 × 13] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Brand : chr [1:25600] "Starbucks" "Starbucks" "Starbucks" "Starbucks" ...
## $ Store Number : chr [1:25600] "47370-257954" "22331-212325" "47089-256771" "22126-218024" ...
## $ Store Name : chr [1:25600] "Meritxell, 96" "Ajman Drive Thru" "Dana Mall" "Twofour 54" ...
## $ Ownership Type: chr [1:25600] "Licensed" "Licensed" "Licensed" "Licensed" ...
## $ Street Address: chr [1:25600] "Av. Meritxell, 96" "1 Street 69, Al Jarf" "Sheikh Khalifa Bin Zayed St." "Al Salam Street" ...
## $ City : chr [1:25600] "Andorra la Vella" "Ajman" "Ajman" "Abu Dhabi" ...
## $ State/Province: chr [1:25600] "7" "AJ" "AJ" "AZ" ...
## $ Country : chr [1:25600] "AD" "AE" "AE" "AE" ...
## $ Postcode : chr [1:25600] "AD500" NA NA NA ...
## $ Phone Number : chr [1:25600] "376818720" NA NA NA ...
## $ Timezone : chr [1:25600] "GMT+1:00 Europe/Andorra" "GMT+04:00 Asia/Dubai" "GMT+04:00 Asia/Dubai" "GMT+04:00 Asia/Dubai" ...
## $ Longitude : num [1:25600] 1.53 55.47 55.47 54.38 54.54 ...
## $ Latitude : num [1:25600] 42.5 25.4 25.4 24.5 24.5 ...
## - attr(*, "spec")=
## .. cols(
## .. Brand = col_character(),
## .. `Store Number` = col_character(),
## .. `Store Name` = col_character(),
## .. `Ownership Type` = col_character(),
## .. `Street Address` = col_character(),
## .. City = col_character(),
## .. `State/Province` = col_character(),
## .. Country = col_character(),
## .. Postcode = col_character(),
## .. `Phone Number` = col_character(),
## .. Timezone = col_character(),
## .. Longitude = col_double(),
## .. Latitude = col_double()
## .. )
## - attr(*, "problems")=<externalptr>
str(sb_nutr)
## spc_tbl_ [205 × 7] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Item : chr [1:205] "Chonga Bagel" "8-Grain Roll" "Almond Croissant" "Apple Fritter" ...
## $ Category : chr [1:205] "Food" "Food" "Food" "Food" ...
## $ Calories : num [1:205] 300 380 410 460 420 380 420 240 350 320 ...
## $ Fat (g) : num [1:205] 5 6 22 23 22 16 17 12 22 16 ...
## $ Carb. (g) : num [1:205] 50 70 45 56 52 53 61 28 38 36 ...
## $ Fiber (g) : num [1:205] 3 7 3 2 2 1 2 1 0 1 ...
## $ Protein (g): num [1:205] 12 10 10 7 6 6 5 5 2 8 ...
## - attr(*, "spec")=
## .. cols(
## .. Item = col_character(),
## .. Category = col_character(),
## .. Calories = col_double(),
## .. `Fat (g)` = col_double(),
## .. `Carb. (g)` = col_double(),
## .. `Fiber (g)` = col_double(),
## .. `Protein (g)` = col_double()
## .. )
## - attr(*, "problems")=<externalptr>
str(usa_pop)
## spc_tbl_ [55 × 2] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ state : chr [1:55] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## $ population: num [1:55] 4779736 710231 6392017 2915918 37253956 ...
## - attr(*, "spec")=
## .. cols(
## .. state = col_character(),
## .. population = col_double()
## .. )
## - attr(*, "problems")=<externalptr>
str(usa_states)
## spc_tbl_ [51 × 2] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ State : chr [1:51] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## $ Abbreviation: chr [1:51] "AL" "AK" "AZ" "AR" ...
## - attr(*, "spec")=
## .. cols(
## .. State = col_character(),
## .. Abbreviation = col_character()
## .. )
## - attr(*, "problems")=<externalptr>
sb_usa <- sb_locs |> filter(Country == "US")
sb_usa <- sb_usa %>%
rename(state = 'State/Province')
sb_locs_state <- sb_usa |>
group_by(state) |>
summarize(Store_Count = n())
# need state abbreviations
usa_pop_abbr <-
full_join(usa_pop, usa_states, by=c("state"="State"))
sb_locs_state <- full_join(sb_locs_state, usa_pop_abbr, by= c("state"="Abbreviation"))
ggplotly for EDAAnswer the following questions:
Are the number of Starbucks proportional to the population of a state? (scatterplot)
Is the caloric distribution of Starbucks menu items different for drinks and food? (histogram)
What are the top 20 words in Starbucks menu items? (bar plot)
ggplot(sb_locs_state, aes(x = population, y = Store_Count)) +
geom_point() + # Add points to represent each state
labs(x = "Population", y = "Number of Starbucks Stores", title = "Starbucks Stores vs Population by State")
## Warning: Removed 4 rows containing missing values or values outside the scale range
## (`geom_point()`).
We can observe a linear relationship between population and the number of stores, indicating that the number of Starbucks stores is proportional to the population of a state.
drinks <- sb_nutr[sb_nutr$Category == "Drinks", ]
food <- sb_nutr[sb_nutr$Category == "Food", ]
# Create histograms for drinks and food
ggplot() +
geom_histogram(data = drinks, aes(x = Calories), bins = 30, fill = "blue", alpha = 0.7) +
geom_histogram(data = food, aes(x = Calories), bins = 30, fill = "orange", alpha = 0.7) +
labs(x = "Calories", y = "Frequency", title = "Caloric Distribution of Starbucks Menu Items") +
scale_fill_manual(values = c("blue", "orange"), name = "Category", labels = c("Drinks", "Food")) +
theme_minimal()
We can observe that the caloric distribution of Starbucks menu items differs between drinks and food. Food items tend to have more calories than drinks.
# Tokenize the text into words
word_counts <- sb_nutr %>%
unnest_tokens(word, Item) %>%
count(word, sort = TRUE)
# Select the top 20 words
top_20_words <- word_counts %>%
slice_head(n = 20)
# Create a bar plot
ggplot(top_20_words, aes(x = reorder(word, n), y = n)) +
geom_col(fill = "skyblue") +
coord_flip() +
labs(x = "Word", y = "Frequency", title = "Top 20 Words in Starbucks Menu Items")
plot_ly()plot_ly() representing the
relationship between calories and carbssb_nutr <- sb_nutr %>%
rename(Carbs = 'Carb. (g)')
sb_nutr <- sb_nutr %>%
rename(Fat = 'Fat (g)')
sb_nutr <- sb_nutr %>%
rename(Fiber = 'Fiber (g)')
sb_nutr <- sb_nutr %>%
rename(Protein = 'Protein (g)')
scatterplot <- plot_ly(sb_nutr, x = ~Calories, y = ~Carbs, color = ~Category, colors = c("blue", "orange")) %>%
add_markers() %>%
layout(xaxis = list(title = "Calories"), yaxis = list(title = "Carbs"), title = "Calories vs Carbs by Category")
scatterplot
hovermode = "compare"# Tokenize the text into words
word_counts <- sb_nutr %>%
unnest_tokens(word, Item) %>%
count(word, sort = TRUE)
# Select the top 10 words
top_10_words <- word_counts %>%
slice_head(n = 10) %>%
pull(word)
top_10_words_lower <- tolower(top_10_words)
# Filter items containing the top 10 words
filtered_items <- sb_nutr %>%
filter(str_detect(tolower(Item), paste(top_10_words, collapse = "|")))
# Create a scatterplot
scatterplot <- plot_ly(filtered_items, x = ~Calories, y = ~Carbs, color = ~Category, colors = c("blue", "orange")) %>%
add_markers(text = ~Item, hoverinfo = "text") %>%
layout(xaxis = list(title = "Calories"),
yaxis = list(title = "Carbs"),
title = "Calories vs Carbs for Items with Top 10 Words",
hovermode = "compare")
scatterplot
plot_ly Boxplots# Create a new column indicating which top 10 word is present in each item
sb_nutr <- sb_nutr %>%
mutate(top_word = str_extract(tolower(Item), paste(top_10_words_lower, collapse = "|")))
# Convert the top_word column to a factor
# sb_nutr$top_word <- factor(sb_nutr$top_word)
# sb_nutr$Category <- as.factor(sb_nutr$Category)
# Reshape the data for plotting
sb_nutr_long <- sb_nutr %>%
select(-Item) %>%
pivot_longer(cols = c(Carbs, Fat, Fiber, Protein), names_to = "nutritional_variable", values_to = "value")
# Create the boxplot
ggplot(sb_nutr_long, aes(x = top_word, y = value, fill = top_word)) +
geom_boxplot() +
facet_wrap(~ nutritional_variable, scales = "free") +
labs(x = "Top 10 Words", y = "Value", fill = "Top 10 Words",
title = "Boxplot of Nutritional Variables by Top 10 Item Words") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
scatterplot_3d <- plot_ly(filtered_items, x = ~Calories, y = ~Carbs, z = ~Protein,
type = "scatter3d", mode = "markers",
marker = list(size = 5)) %>%
layout(scene = list(xaxis = list(title = "Calories"),
yaxis = list(title = "Carbs"),
zaxis = list(title = "Protein")),
title = "3D Scatterplot of Calories, Carbs, and Protein for Items Containing Top 10 Words")
scatterplot_3d
We can see that there is a positive relationship between calories and protein, as well as a positive relationship between calories and carbs. It is hard to tell whether there is a relationship between carbs and protein.
plot_ly Map# Set up mapping details
set_map_details <- list(
scope = 'usa',
projection = list(type = 'albers usa'),
showlakes = TRUE,
lakecolor = toRGB('steelblue')
)
# Make sure both maps are on the same color scale
shadeLimit <- 125
loc_filtered <- sb_locs_state[!is.na(sb_locs_state$Store_Count), ]
# Create hover text for map 1
hover_text_map1 <- with(sb_locs_state, paste("Number of Starbucks: ", Store_Count, '<br>', "State: ", state.y, '<br>'))
# Create the map for number of stores per state
map1 <- plot_geo(locationmode = 'USA-states') %>%
add_trace(data = sb_locs_state,
z = ~Store_Count, # Values to represent on the map
locations = ~state, # Locations (state names)
text = hover_text_map1, # Hover text
color = ~Store_Count,
colors = 'Blues', # Color scale
colorbar = list(title = "Number of Starbucks")) %>%
layout(title = "Number of Starbucks Stores per State", geo = set_map_details)
# Create hover text for map 2
hover_text_map2 <- with(sb_locs_state, paste("Population: ", population, '<br>', "State: ", state.y, '<br>'))
# Create the map for population by state
map2 <- plot_geo(locationmode = 'USA-states') %>%
add_trace(data = sb_locs_state,
z = ~population, # Values to represent on the map
locations = ~state, # Locations (state names)
text = hover_text_map2, # Hover text
color = ~population,
colors = 'Blues', # Color scale
colorbar = list(title = "Population")) %>%
layout(title = "Population by State", geo = set_map_details)
# Display the subplot
subplot(map1, map2)
## Warning: Ignoring 4 observations
We can observe that states with large populations also have a significant number of Starbucks stores, further indicating a proportional relationship.